papers

Publications (15)

cs.LG2026

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

Pengxuan Yang, Yupeng Zheng, Deheng Qian +11

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps…

cs.CV2025

TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning

Zebin Xing, Pengxuan Yang, Linbo Wang +12

Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous…

cs.RO2025

UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty

Pengxuan Yang, Yupeng Zheng, Qichao Zhang +6

End-to-end autonomous driving aims to produce planning trajectories from raw sensors directly. Currently, most approaches integrate perception, prediction, and planning modules int…

cs.RO2025

Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving

Zebin Xing, Yupeng Zheng, Qichao Zhang +5

End-to-end autonomous driving has emerged as a pivotal direction in the field of autonomous systems. Recent works have demonstrated impressive performance by incorporating high-lev…

cs.RO2026

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives

Junli Wang, Zhihua Hua, Xueyi Liu +7

Existing imitation learning methods for end-to-end autonomous driving predominantly learn from successful demonstrations by minimizing geometric deviations from expert trajectories…

cs.CV2025

ComDrive: Comfort-Oriented End-to-End Autonomous Driving

Junming Wang, Xingyu Zhang, Zebin Xing +7

We propose ComDrive: the first comfort-oriented end-to-end autonomous driving system to generate temporally consistent and comfortable trajectories. Recent studies have demonstrate…

cs.CV2025

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

Zebin Xing, Xingyu Zhang, Yang Hu +5

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable…

cs.CV2025

OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity

Junming Wang, Wei Yin, Xiaoxiao Long +4

3D semantic occupancy prediction networks have demonstrated remarkable capabilities in reconstructing the geometric and semantic structure of 3D scenes, providing crucial informati…

cs.CV2026

Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

Linbo Wang, Yupeng Zheng, Qiang Chen +13

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world re…

cs.RO2026

PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance

Yupeng Zheng, Xiang Li, Songen Gu +12

Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency and a lack of high-level know…

cs.RO2024

PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning

Yupeng Zheng, Zebin Xing, Qichao Zhang +8

Vehicle motion planning is an essential component of autonomous driving technology. Current rule-based vehicle motion planning methods perform satisfactorily in common scenarios bu…

cs.RO2026

WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos

Jiahao Liu, Zhongpu Xia, Shuai Tian +13

WALA is a framework that learns executable latent actions for robot manipulation by pretraining on both action‑labeled demonstrations and unlabeled videos, predicting future change…

#latent action learning#video pretraining#robot manipulation#vision-language models
cs.CV2025

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng, Pengxuan Yang, Zebin Xing +8

End-to-end autonomous driving directly generates planning trajectories from raw sensor data, yet it typically relies on costly perception supervision to extract scene information.…

cs.CR2023

SemProtector: A Unified Framework for Semantic Protection in Deep Learning-based Semantic Communication Systems

Xinghan Liu, Guoshun Nan, Qimei Cui +6

Recently proliferated semantic communications (SC) aim at effectively transmitting the semantics conveyed by the source and accurately interpreting the meaning at the destination.…

cs.CV2026

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving

Junli Wang, Yinan Zheng, Xueyi Liu +9

Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of dr…